Hsien-Ting Cheng

Learn More
This paper presents an effective method to combine speech recognition, speaker verification and face verification for biometric authentication. Our method provides a light-weight enrollment process and an easy-to-use verification interface. A multi-face/single-sentence strategy is used to combine voice and face verification modules, and support vector(More)
Privacy protection on user context is one of the most important issues in ubiquitous and pervasive computing. This paper describes a new privacy protection approach that not only filters and reduces the granularity of context information to correct access level granularity, but also intelligently replace the filtered-out context information with the(More)
We propose a method called asymmetric bagging with vector complementary ordering (ABVCO) to handle the class unbalanced problem. The proposed approach is not dependent on artificially generated data or re-weighted data. It can avoid the synthesis of classifiers that favor the majority class. The method is applied to multi-modal biometric authentication for(More)
  • 1